Average Reward Dynamic Programming

Average Reward Dynamic Programming is a dynamic programming method that specifically addresses infinite-horizon Markov decision processes by optimizing the long-run average reward per time step, distinguishing it from alternative criteria such as discounted or total reward formulations.

Publications

2.8K

Citations

Authors

Institutions

Publications per year

2017–2026

Parents

Average Reward Criteria

Publications

Average reward reinforcement learning: Foundations, algorithms, and empirical results

Sridhar Mahadevan · Machine Learning · 1996 · 401 citations · Full text

Business, Computer Science, Artificial Intelligence +13

Simulation-based optimization of Markov reward processes

Peter Marbach, John N. Tsitsiklis · IEEE Transactions on Automatic Control · 2001 · 320 citations · Full text

Business, Decision Sciences, Algorithms +16

Solving Semi-Markov Decision Problems Using Average Reward Reinforcement Learning

Tapas K. Das, Abhijit Gosavi, Sridhar Mahadevan et al. · Management Science · 1999 · 220 citations

Business, Decision Sciences, Algorithms +15

On Dynamic Programming with Unbounded Rewards

Steven A. Lippman · Management Science · 1975 · 167 citations

Business, Decision Sciences, Mathematics +17

Call admission control and routing in integrated services networks using neuro-dynamic programming

Peter Marbach, Oliver Mihatsch, John N. Tsitsiklis · IEEE Journal on Selected Areas in Communications · 2000 · 136 citations

Computing, Computer Science, Computer Networks +12

1–5 of 52

Authors

JN
John N. Tsitsiklis
Massachusetts Institute of Technology, United States
4 publications · 497 citations
4
h-index
PM
Peter Marbach
University of Toronto, Canada
4 publications · 497 citations
4
h-index
SZ
Shlomo Zilberstein
University of Massachusetts Amherst, United States
3 publications · 77 citations
3
h-index
AG
Abhijit Gosavi
Missouri University of Science and Technology, United States
3 publications · 340 citations
3
h-index
SM
Sridhar Mahadevan
University of Massachusetts Amherst, United States
3 publications · 642 citations
3
h-index

1–5 of 88

Institutions

1–8 of 64

Venues

Machine Learning
3 publications · 518 citations
3
h-index
IEEE Transactions on Automatic Control
3 publications · 359 citations
3
h-index
arXiv (Cornell University)
Repository · 2 publications · 65 citations
2
h-index
Systems & Control Letters
2 publications · 59 citations
2
h-index
Mathematical Methods of Operations Research
2 publications · 28 citations
2
h-index

1–5